Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmbert_tiny-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
7e91148
•
1 Parent(s): 4b4ef97

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697667313.46dc0c540dd0.3571.4 +3 -0
  5. test.tsv +0 -0
  6. training.log +243 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c42c18aed49bb616bb1ab95e9477bc8d84c955003b9c48c69cbcf68456d479a
3
+ size 19045922
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 22:15:39 0.0000 0.7469 0.2807 0.0000 0.0000 0.0000 0.0000
3
+ 2 22:16:05 0.0000 0.2162 0.2369 0.5733 0.2304 0.3287 0.2013
4
+ 3 22:16:31 0.0000 0.1913 0.2541 0.6433 0.2180 0.3256 0.1983
5
+ 4 22:16:57 0.0000 0.1772 0.2133 0.5628 0.3564 0.4364 0.2906
6
+ 5 22:17:23 0.0000 0.1647 0.2064 0.5014 0.3802 0.4324 0.2914
7
+ 6 22:17:49 0.0000 0.1587 0.1998 0.4912 0.4329 0.4602 0.3153
8
+ 7 22:18:15 0.0000 0.1543 0.2065 0.5394 0.4029 0.4613 0.3135
9
+ 8 22:18:41 0.0000 0.1489 0.2008 0.5242 0.4256 0.4698 0.3214
10
+ 9 22:19:07 0.0000 0.1462 0.1970 0.5053 0.4411 0.4710 0.3235
11
+ 10 22:19:33 0.0000 0.1450 0.1991 0.5143 0.4287 0.4676 0.3197
runs/events.out.tfevents.1697667313.46dc0c540dd0.3571.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ae8b1b91277e6916b086d6691e13481fda04b568d2a23335dbb014605b68a2c
3
+ size 808480
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 22:15:13,407 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 22:15:13,407 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-18 22:15:13,407 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 22:15:13,407 MultiCorpus: 5777 train + 722 dev + 723 test sentences
52
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
53
+ 2023-10-18 22:15:13,407 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 22:15:13,407 Train: 5777 sentences
55
+ 2023-10-18 22:15:13,407 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 22:15:13,407 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 22:15:13,407 Training Params:
58
+ 2023-10-18 22:15:13,407 - learning_rate: "3e-05"
59
+ 2023-10-18 22:15:13,407 - mini_batch_size: "4"
60
+ 2023-10-18 22:15:13,407 - max_epochs: "10"
61
+ 2023-10-18 22:15:13,407 - shuffle: "True"
62
+ 2023-10-18 22:15:13,407 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 22:15:13,407 Plugins:
64
+ 2023-10-18 22:15:13,407 - TensorboardLogger
65
+ 2023-10-18 22:15:13,407 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 22:15:13,408 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 22:15:13,408 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 22:15:13,408 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 22:15:13,408 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 22:15:13,408 Computation:
71
+ 2023-10-18 22:15:13,408 - compute on device: cuda:0
72
+ 2023-10-18 22:15:13,408 - embedding storage: none
73
+ 2023-10-18 22:15:13,408 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 22:15:13,408 Model training base path: "hmbench-icdar/nl-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-18 22:15:13,408 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 22:15:13,408 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 22:15:13,408 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 22:15:15,962 epoch 1 - iter 144/1445 - loss 2.39314632 - time (sec): 2.55 - samples/sec: 7270.88 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-18 22:15:18,317 epoch 1 - iter 288/1445 - loss 2.14684515 - time (sec): 4.91 - samples/sec: 7182.74 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-18 22:15:20,799 epoch 1 - iter 432/1445 - loss 1.76829385 - time (sec): 7.39 - samples/sec: 7053.44 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-18 22:15:23,263 epoch 1 - iter 576/1445 - loss 1.43081858 - time (sec): 9.85 - samples/sec: 7146.25 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-18 22:15:25,690 epoch 1 - iter 720/1445 - loss 1.21350836 - time (sec): 12.28 - samples/sec: 7143.92 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-18 22:15:28,172 epoch 1 - iter 864/1445 - loss 1.06801420 - time (sec): 14.76 - samples/sec: 7135.56 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-18 22:15:30,643 epoch 1 - iter 1008/1445 - loss 0.95360992 - time (sec): 17.23 - samples/sec: 7166.69 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-18 22:15:33,003 epoch 1 - iter 1152/1445 - loss 0.87386994 - time (sec): 19.60 - samples/sec: 7184.61 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-18 22:15:35,453 epoch 1 - iter 1296/1445 - loss 0.80394806 - time (sec): 22.05 - samples/sec: 7197.68 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-18 22:15:37,856 epoch 1 - iter 1440/1445 - loss 0.74866431 - time (sec): 24.45 - samples/sec: 7186.43 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-18 22:15:37,934 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 22:15:37,934 EPOCH 1 done: loss 0.7469 - lr: 0.000030
90
+ 2023-10-18 22:15:39,177 DEV : loss 0.2806679308414459 - f1-score (micro avg) 0.0
91
+ 2023-10-18 22:15:39,191 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 22:15:41,536 epoch 2 - iter 144/1445 - loss 0.27792179 - time (sec): 2.34 - samples/sec: 6994.31 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-18 22:15:43,948 epoch 2 - iter 288/1445 - loss 0.23375750 - time (sec): 4.76 - samples/sec: 7259.12 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-18 22:15:46,367 epoch 2 - iter 432/1445 - loss 0.22939829 - time (sec): 7.18 - samples/sec: 7373.97 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-18 22:15:48,717 epoch 2 - iter 576/1445 - loss 0.22226944 - time (sec): 9.53 - samples/sec: 7411.64 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-18 22:15:51,131 epoch 2 - iter 720/1445 - loss 0.22022531 - time (sec): 11.94 - samples/sec: 7351.84 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-18 22:15:53,833 epoch 2 - iter 864/1445 - loss 0.21955073 - time (sec): 14.64 - samples/sec: 7177.20 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-18 22:15:56,214 epoch 2 - iter 1008/1445 - loss 0.22076945 - time (sec): 17.02 - samples/sec: 7144.54 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-18 22:15:58,820 epoch 2 - iter 1152/1445 - loss 0.21903683 - time (sec): 19.63 - samples/sec: 7152.33 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-18 22:16:01,266 epoch 2 - iter 1296/1445 - loss 0.21933025 - time (sec): 22.07 - samples/sec: 7115.29 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-18 22:16:03,826 epoch 2 - iter 1440/1445 - loss 0.21626617 - time (sec): 24.63 - samples/sec: 7132.47 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-18 22:16:03,904 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 22:16:03,904 EPOCH 2 done: loss 0.2162 - lr: 0.000027
104
+ 2023-10-18 22:16:05,672 DEV : loss 0.23692606389522552 - f1-score (micro avg) 0.3287
105
+ 2023-10-18 22:16:05,687 saving best model
106
+ 2023-10-18 22:16:05,718 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 22:16:08,206 epoch 3 - iter 144/1445 - loss 0.19237069 - time (sec): 2.49 - samples/sec: 6801.18 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-18 22:16:10,568 epoch 3 - iter 288/1445 - loss 0.20044421 - time (sec): 4.85 - samples/sec: 7017.71 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-18 22:16:13,038 epoch 3 - iter 432/1445 - loss 0.20343289 - time (sec): 7.32 - samples/sec: 7328.74 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-18 22:16:15,337 epoch 3 - iter 576/1445 - loss 0.20071860 - time (sec): 9.62 - samples/sec: 7316.26 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-18 22:16:17,741 epoch 3 - iter 720/1445 - loss 0.19738794 - time (sec): 12.02 - samples/sec: 7323.13 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-18 22:16:20,177 epoch 3 - iter 864/1445 - loss 0.19558068 - time (sec): 14.46 - samples/sec: 7277.40 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-18 22:16:22,657 epoch 3 - iter 1008/1445 - loss 0.19494579 - time (sec): 16.94 - samples/sec: 7339.32 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-18 22:16:24,966 epoch 3 - iter 1152/1445 - loss 0.19436800 - time (sec): 19.25 - samples/sec: 7309.17 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-18 22:16:27,470 epoch 3 - iter 1296/1445 - loss 0.19204889 - time (sec): 21.75 - samples/sec: 7305.79 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-18 22:16:29,826 epoch 3 - iter 1440/1445 - loss 0.19140078 - time (sec): 24.11 - samples/sec: 7287.40 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-18 22:16:29,906 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 22:16:29,906 EPOCH 3 done: loss 0.1913 - lr: 0.000023
119
+ 2023-10-18 22:16:31,653 DEV : loss 0.2540631890296936 - f1-score (micro avg) 0.3256
120
+ 2023-10-18 22:16:31,668 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-18 22:16:34,014 epoch 4 - iter 144/1445 - loss 0.17625734 - time (sec): 2.35 - samples/sec: 7496.14 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-18 22:16:36,430 epoch 4 - iter 288/1445 - loss 0.16013685 - time (sec): 4.76 - samples/sec: 7586.55 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-18 22:16:38,804 epoch 4 - iter 432/1445 - loss 0.16861437 - time (sec): 7.14 - samples/sec: 7450.16 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-18 22:16:41,070 epoch 4 - iter 576/1445 - loss 0.16940708 - time (sec): 9.40 - samples/sec: 7533.32 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-18 22:16:43,335 epoch 4 - iter 720/1445 - loss 0.17263654 - time (sec): 11.67 - samples/sec: 7472.43 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-18 22:16:45,874 epoch 4 - iter 864/1445 - loss 0.17443784 - time (sec): 14.21 - samples/sec: 7423.53 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-18 22:16:48,244 epoch 4 - iter 1008/1445 - loss 0.17680417 - time (sec): 16.58 - samples/sec: 7427.32 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-18 22:16:50,606 epoch 4 - iter 1152/1445 - loss 0.17608810 - time (sec): 18.94 - samples/sec: 7413.92 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-18 22:16:52,990 epoch 4 - iter 1296/1445 - loss 0.17675409 - time (sec): 21.32 - samples/sec: 7379.58 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-18 22:16:55,447 epoch 4 - iter 1440/1445 - loss 0.17717412 - time (sec): 23.78 - samples/sec: 7385.67 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-18 22:16:55,531 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-18 22:16:55,531 EPOCH 4 done: loss 0.1772 - lr: 0.000020
133
+ 2023-10-18 22:16:57,593 DEV : loss 0.21325278282165527 - f1-score (micro avg) 0.4364
134
+ 2023-10-18 22:16:57,607 saving best model
135
+ 2023-10-18 22:16:57,642 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-18 22:17:00,004 epoch 5 - iter 144/1445 - loss 0.16636630 - time (sec): 2.36 - samples/sec: 7283.76 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-18 22:17:02,528 epoch 5 - iter 288/1445 - loss 0.15766715 - time (sec): 4.88 - samples/sec: 7419.05 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-18 22:17:04,918 epoch 5 - iter 432/1445 - loss 0.15448021 - time (sec): 7.27 - samples/sec: 7341.91 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-18 22:17:07,397 epoch 5 - iter 576/1445 - loss 0.15950395 - time (sec): 9.75 - samples/sec: 7339.99 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-18 22:17:09,810 epoch 5 - iter 720/1445 - loss 0.16067601 - time (sec): 12.17 - samples/sec: 7397.82 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-18 22:17:12,001 epoch 5 - iter 864/1445 - loss 0.16175646 - time (sec): 14.36 - samples/sec: 7517.75 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-18 22:17:14,235 epoch 5 - iter 1008/1445 - loss 0.16105262 - time (sec): 16.59 - samples/sec: 7524.87 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-18 22:17:16,662 epoch 5 - iter 1152/1445 - loss 0.16316996 - time (sec): 19.02 - samples/sec: 7536.66 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-18 22:17:19,015 epoch 5 - iter 1296/1445 - loss 0.16557631 - time (sec): 21.37 - samples/sec: 7486.45 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-18 22:17:21,350 epoch 5 - iter 1440/1445 - loss 0.16498905 - time (sec): 23.71 - samples/sec: 7403.27 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-18 22:17:21,438 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-18 22:17:21,438 EPOCH 5 done: loss 0.1647 - lr: 0.000017
148
+ 2023-10-18 22:17:23,208 DEV : loss 0.20644906163215637 - f1-score (micro avg) 0.4324
149
+ 2023-10-18 22:17:23,222 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-18 22:17:25,647 epoch 6 - iter 144/1445 - loss 0.17082670 - time (sec): 2.42 - samples/sec: 7555.88 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-18 22:17:28,129 epoch 6 - iter 288/1445 - loss 0.16750043 - time (sec): 4.91 - samples/sec: 7212.45 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-18 22:17:30,591 epoch 6 - iter 432/1445 - loss 0.17029904 - time (sec): 7.37 - samples/sec: 7130.80 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-18 22:17:33,171 epoch 6 - iter 576/1445 - loss 0.16210786 - time (sec): 9.95 - samples/sec: 7113.75 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-18 22:17:35,596 epoch 6 - iter 720/1445 - loss 0.15996811 - time (sec): 12.37 - samples/sec: 7192.79 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-18 22:17:37,952 epoch 6 - iter 864/1445 - loss 0.16028998 - time (sec): 14.73 - samples/sec: 7181.61 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-18 22:17:40,277 epoch 6 - iter 1008/1445 - loss 0.16103140 - time (sec): 17.05 - samples/sec: 7197.95 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-18 22:17:42,653 epoch 6 - iter 1152/1445 - loss 0.16240655 - time (sec): 19.43 - samples/sec: 7226.49 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-18 22:17:45,046 epoch 6 - iter 1296/1445 - loss 0.15993163 - time (sec): 21.82 - samples/sec: 7245.37 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-18 22:17:47,386 epoch 6 - iter 1440/1445 - loss 0.15859787 - time (sec): 24.16 - samples/sec: 7262.98 - lr: 0.000013 - momentum: 0.000000
160
+ 2023-10-18 22:17:47,478 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-18 22:17:47,478 EPOCH 6 done: loss 0.1587 - lr: 0.000013
162
+ 2023-10-18 22:17:49,275 DEV : loss 0.19981378316879272 - f1-score (micro avg) 0.4602
163
+ 2023-10-18 22:17:49,290 saving best model
164
+ 2023-10-18 22:17:49,327 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-18 22:17:51,814 epoch 7 - iter 144/1445 - loss 0.15298779 - time (sec): 2.49 - samples/sec: 6654.90 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-18 22:17:54,333 epoch 7 - iter 288/1445 - loss 0.15264329 - time (sec): 5.00 - samples/sec: 7121.17 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-18 22:17:56,774 epoch 7 - iter 432/1445 - loss 0.15380859 - time (sec): 7.45 - samples/sec: 7220.78 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-18 22:17:59,139 epoch 7 - iter 576/1445 - loss 0.15272071 - time (sec): 9.81 - samples/sec: 7239.52 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-18 22:18:01,538 epoch 7 - iter 720/1445 - loss 0.15533373 - time (sec): 12.21 - samples/sec: 7244.29 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-18 22:18:03,695 epoch 7 - iter 864/1445 - loss 0.15379752 - time (sec): 14.37 - samples/sec: 7386.12 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-18 22:18:05,960 epoch 7 - iter 1008/1445 - loss 0.15411990 - time (sec): 16.63 - samples/sec: 7428.33 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-18 22:18:08,406 epoch 7 - iter 1152/1445 - loss 0.15631995 - time (sec): 19.08 - samples/sec: 7477.96 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-18 22:18:10,797 epoch 7 - iter 1296/1445 - loss 0.15702230 - time (sec): 21.47 - samples/sec: 7414.47 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-18 22:18:13,172 epoch 7 - iter 1440/1445 - loss 0.15433279 - time (sec): 23.84 - samples/sec: 7372.37 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-18 22:18:13,250 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-18 22:18:13,250 EPOCH 7 done: loss 0.1543 - lr: 0.000010
177
+ 2023-10-18 22:18:15,383 DEV : loss 0.20650173723697662 - f1-score (micro avg) 0.4613
178
+ 2023-10-18 22:18:15,397 saving best model
179
+ 2023-10-18 22:18:15,432 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-18 22:18:17,902 epoch 8 - iter 144/1445 - loss 0.17182834 - time (sec): 2.47 - samples/sec: 7720.37 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-18 22:18:20,373 epoch 8 - iter 288/1445 - loss 0.16207302 - time (sec): 4.94 - samples/sec: 7399.34 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-18 22:18:22,749 epoch 8 - iter 432/1445 - loss 0.15599699 - time (sec): 7.32 - samples/sec: 7254.95 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-18 22:18:25,114 epoch 8 - iter 576/1445 - loss 0.16015713 - time (sec): 9.68 - samples/sec: 7189.52 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-18 22:18:27,471 epoch 8 - iter 720/1445 - loss 0.15628888 - time (sec): 12.04 - samples/sec: 7161.34 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-18 22:18:29,816 epoch 8 - iter 864/1445 - loss 0.15567396 - time (sec): 14.38 - samples/sec: 7204.07 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-18 22:18:32,111 epoch 8 - iter 1008/1445 - loss 0.15296437 - time (sec): 16.68 - samples/sec: 7302.17 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-18 22:18:34,490 epoch 8 - iter 1152/1445 - loss 0.15205419 - time (sec): 19.06 - samples/sec: 7357.23 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-18 22:18:36,881 epoch 8 - iter 1296/1445 - loss 0.15117031 - time (sec): 21.45 - samples/sec: 7361.91 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-18 22:18:39,320 epoch 8 - iter 1440/1445 - loss 0.14875319 - time (sec): 23.89 - samples/sec: 7355.33 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-18 22:18:39,405 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-18 22:18:39,405 EPOCH 8 done: loss 0.1489 - lr: 0.000007
192
+ 2023-10-18 22:18:41,182 DEV : loss 0.2007928192615509 - f1-score (micro avg) 0.4698
193
+ 2023-10-18 22:18:41,197 saving best model
194
+ 2023-10-18 22:18:41,233 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-18 22:18:43,612 epoch 9 - iter 144/1445 - loss 0.13803425 - time (sec): 2.38 - samples/sec: 7192.10 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-18 22:18:45,994 epoch 9 - iter 288/1445 - loss 0.13390889 - time (sec): 4.76 - samples/sec: 7388.05 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-18 22:18:48,274 epoch 9 - iter 432/1445 - loss 0.14039521 - time (sec): 7.04 - samples/sec: 7375.77 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-18 22:18:50,726 epoch 9 - iter 576/1445 - loss 0.13920635 - time (sec): 9.49 - samples/sec: 7421.14 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-18 22:18:53,125 epoch 9 - iter 720/1445 - loss 0.13962614 - time (sec): 11.89 - samples/sec: 7412.45 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-18 22:18:55,524 epoch 9 - iter 864/1445 - loss 0.14289517 - time (sec): 14.29 - samples/sec: 7323.98 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-18 22:18:57,951 epoch 9 - iter 1008/1445 - loss 0.14366200 - time (sec): 16.72 - samples/sec: 7317.65 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-18 22:19:00,430 epoch 9 - iter 1152/1445 - loss 0.14679698 - time (sec): 19.20 - samples/sec: 7336.73 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-18 22:19:02,838 epoch 9 - iter 1296/1445 - loss 0.14740503 - time (sec): 21.60 - samples/sec: 7335.93 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-18 22:19:05,203 epoch 9 - iter 1440/1445 - loss 0.14602498 - time (sec): 23.97 - samples/sec: 7329.86 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-18 22:19:05,283 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-18 22:19:05,284 EPOCH 9 done: loss 0.1462 - lr: 0.000003
207
+ 2023-10-18 22:19:07,083 DEV : loss 0.19696438312530518 - f1-score (micro avg) 0.471
208
+ 2023-10-18 22:19:07,098 saving best model
209
+ 2023-10-18 22:19:07,138 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-18 22:19:09,593 epoch 10 - iter 144/1445 - loss 0.17038935 - time (sec): 2.45 - samples/sec: 7036.32 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-18 22:19:11,999 epoch 10 - iter 288/1445 - loss 0.15496516 - time (sec): 4.86 - samples/sec: 7198.44 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-18 22:19:14,441 epoch 10 - iter 432/1445 - loss 0.14934365 - time (sec): 7.30 - samples/sec: 7333.86 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-18 22:19:16,858 epoch 10 - iter 576/1445 - loss 0.14818797 - time (sec): 9.72 - samples/sec: 7263.78 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-18 22:19:19,266 epoch 10 - iter 720/1445 - loss 0.14649527 - time (sec): 12.13 - samples/sec: 7274.87 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-18 22:19:21,642 epoch 10 - iter 864/1445 - loss 0.14868735 - time (sec): 14.50 - samples/sec: 7264.03 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-18 22:19:24,031 epoch 10 - iter 1008/1445 - loss 0.14662905 - time (sec): 16.89 - samples/sec: 7265.70 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-18 22:19:26,493 epoch 10 - iter 1152/1445 - loss 0.14401068 - time (sec): 19.35 - samples/sec: 7295.78 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 22:19:28,722 epoch 10 - iter 1296/1445 - loss 0.14499991 - time (sec): 21.58 - samples/sec: 7392.64 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-18 22:19:31,128 epoch 10 - iter 1440/1445 - loss 0.14488256 - time (sec): 23.99 - samples/sec: 7327.85 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 22:19:31,208 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-18 22:19:31,208 EPOCH 10 done: loss 0.1450 - lr: 0.000000
222
+ 2023-10-18 22:19:33,334 DEV : loss 0.19905780255794525 - f1-score (micro avg) 0.4676
223
+ 2023-10-18 22:19:33,378 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-18 22:19:33,378 Loading model from best epoch ...
225
+ 2023-10-18 22:19:33,459 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
226
+ 2023-10-18 22:19:34,792
227
+ Results:
228
+ - F-score (micro) 0.4923
229
+ - F-score (macro) 0.3343
230
+ - Accuracy 0.3404
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ LOC 0.5121 0.6463 0.5714 458
236
+ PER 0.5556 0.3527 0.4315 482
237
+ ORG 0.0000 0.0000 0.0000 69
238
+
239
+ micro avg 0.5271 0.4618 0.4923 1009
240
+ macro avg 0.3559 0.3330 0.3343 1009
241
+ weighted avg 0.4978 0.4618 0.4655 1009
242
+
243
+ 2023-10-18 22:19:34,792 ----------------------------------------------------------------------------------------------------